Hotjar MCP Server: Give AI Agents Access to Your Heatmaps and User Feedback

Why Give AI Access to Hotjar?

Hotjar is the behavior analytics tool over a million websites use for heatmaps, session recordings, surveys, and user feedback. When building UX improvements or debugging user flows, you switch between your editor and Hotjar to check click patterns, read survey responses, review rage click data, and watch recordings. Each context switch costs focus during development.

An MCP server turns your Hotjar workspace into structured tools that AI coding assistants (Claude, Cursor, Windsurf) can call directly. Instead of switching to Hotjar to check a heatmap or read feedback, your AI reads them in real-time while you work.

What AI Agents Can Do with Hotjar Access

With a DataFaucet MCP server pointed at your Hotjar account, AI tools can:

• Query heatmaps — click data, scroll depth, and engagement zones by page
• Read surveys — response summaries, NPS scores, and open-text feedback
• Check recordings — session metadata, rage clicks, u-turns, and error pages
• Pull feedback — user comments, ratings, and sentiment from feedback widgets
• List funnels — conversion step data and drop-off analysis

Setting Up Hotjar as an MCP Server with DataFaucet

1. Open DataFaucet and start a capture session
2. Navigate to your Hotjar dashboard and browse heatmaps, recordings, surveys, and feedback
3. DataFaucet captures the API patterns Hotjar uses internally
4. Deploy and connect to your AI coding tool

claude mcp add hotjar-analytics https://your-datafaucet-server.dev/sse

Your AI now has structured tool access to your Hotjar behavior data.

Example Queries After Setup

Once connected, ask your AI questions like:

• "Where are users clicking most on the pricing page?"
• "What's the average scroll depth on the landing page?"
• "Summarize the last 20 survey responses about checkout"
• "Which pages have the most rage clicks this week?"
• "What's our current NPS score from the in-app survey?"

Each query returns structured data your AI can use in code, UX decisions, or debugging workflows.

Why DataFaucet Instead of the Hotjar API?

Hotjar's API is limited and primarily designed for data export, not real-time querying. DataFaucet captures from your authenticated session in minutes:

No API limitations. No CSV exports to parse. Full access to everything you see in the Hotjar dashboard.

Use Cases by Role

Frontend engineers — AI surfaces rage click locations and scroll dead zones while you code, informing layout fixes without tab switching.

Product managers — AI pulls NPS trends and survey responses to inform sprint priorities during planning sessions.

UX researchers — AI queries recording metadata to identify high-frustration sessions by page, event type, or user segment.

Works With Any MCP Client

DataFaucet MCP servers are compatible with every MCP client:

• Claude Desktop / Claude Code — claude mcp add
• Cursor — add to .cursor/mcp.json
• Windsurf — add in MCP settings panel
• Any MCP-compatible tool — standard SSE transport

Getting Started

1. Visit DataFaucet
2. Capture your Hotjar dashboard API calls
3. Deploy your MCP server
4. Connect to Claude, Cursor, or Windsurf

Your AI coding assistant now has real-time access to your Hotjar heatmaps, recordings, surveys, and user feedback.